buithehai1994's Projects
Analysing Company Performance with SQL
The goal of this project is to analyse a dataset (made of CSVs and Jsons files) by using a Data Lakehouse with Snowflake. You will have to upload the data on a cloud storage, ingest the data into the Data Lakehouse, perform data transformation and finally analyse it.
The goal of this assignment is to build production-ready data pipelines with Airflow. You will work with two different input datasets that will need to be processed and cleaned before loading this insightful information separately into a data warehouse (using ELT pipelines) and a data mart for analytical purposes
food classifier using pytorch
Handwritten digit recognition using neural network trained on 60000 images from MNIST dataset
A ipynb notebook results in captioning images using Flick8k dataset and Neural Netwiorks
This repository contains the project which we did in one of our college courses named "Pattern Recognition and machine learning"
An attention based sequential deep learning model implemented in pytorch to generate single line caption given an input image
Image Captioning using LSTM and Deep Learning on Flickr8K dataset.
Machine learning algorithms from the scratch - Rakend
The objective of this assessment is to build data science models that yield valuable insights
EPFL Machine Learning Course, Fall 2023
RAG using Llama3, Langchain and ChromaDB
In this assignment, we will tackle a regression problem. We will be working on a dataset consolidated from census data in the USA. The goal is to accurately predict cancer mortality based on information related to US counties.The dataset contains 33 different features (demography, medical information).
A drawable MNIST demo using streamlit.